Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Shaoxiang Zeng has a total of 21 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Spatiotemporal Prediction and Proactive Control Method for Excavation-Induced Wall Deflection

    by Weiwei Liu, Shaoxiang Zeng, Kaiyue Chen, Xiaodong Pan

    The advancement of urbanization has led to stricter requirements for the prediction and control of excavation-induced deformations. To achieve this goal, this study proposes a novel method that integrates a spatiotemporal graph attention network (ST-GAT) with a proportional–integral–derivative (PID) controller to proactively control wall deflections caused by excavation. The ST-GAT model improves wall deflection prediction by capturing spatial relationships between monitoring points near steel struts and dynamically assigning weights based on their importance. The interpretability of the model is greatly improved by generating a feature attribution map across various input features and visualizing the weight distribution between nodes in the GAT network. A proactive control method of wall deflections is proposed by replacing current monitoring values in the PID control system with predicted values for multiple steel struts using the ST-GAT model. Compared to the standard PID method, this approach can control wall deflections before significant deformations occur. A real excavation project equipped with a servo support system is used to validate the effectiveness of the proposed method. The results show that the ST-GAT model significantly outperforms other models, and its performance improves when utilizing spatial relationships from more monitoring points. With a reasonable combination of PID hyperparameters, the proposed ST-GAT-based PID controller can control wall deflections close to a target value.


  • Open Access

    A deep transfer learning model for the deformation of braced excavations with limited monitoring data

    by Yuanqin Tao, Shaoxiang Zeng, Tiantian Ying, Honglei Sun, Sunjuexu Pan, Yuanqiang Cai


  • Open Access

    An interpretable probabilistic prediction algorithm for shield movement performance

    by Yapeng Zhang, Long Liu, Jian Wu, Shaoxiang Zeng, Jianquan Hu, Yuanqin Tao, Yong Huang, Xuetao Zhou, Xu Liang

    Total thrust and torque are two key indicators of shield movement performance. Most existing data-driven machine learning studies focus on developing more accurate models for predicting total thrust and torque but overlook the interpretability of the models. To address this black-box issue, this study proposes an interpretable probabilistic prediction algorithm for the shield movement performance. The algorithm uses the natural gradient boosting (NGBoost) model to iteratively update the parametric probability distributions (e.g., mean and variance) and achieve probabilistic predictions of the total thrust and torque. The impact of each feature on the prediction values and uncertainty is quantified by extending the importance analysis of a single deterministic predictive value to both the mean and variance. The feature interactions are analyzed and their predictive contributions are quantified by the shapley additive explanations (SHAP) method. The transparency of the NGBoost model is improved through the visualization of the decision-making process. A shield tunneling project in Hangzhou is used to validate the effectiveness of the proposed algorithm. The results indicate that the NGboost model outperforms other five models in terms of accuracy. The prediction results are interpretable, and the interpretable probabilistic model provides decision-makers with a more intuitive and reliable reference.


  • Open Access

    An Intelligent Multi-Ring Shield Movement Performance Prediction and Control Method

    by Shaoxiang Zeng, Mengfei Yu, Shanmin Chen, Mengfen Shen

    Accurate control of the shield attitude can ensure precise tunnel excavation and minimize impact on the surrounding areas. However, neglecting the total thrust force may cause excessive disturbance to the strata, leading to collapse. This study proposes a Bayesian optimization-based temporal attention long short-term memory model (BOTA-LSTM) for multi-objective prediction and control of shield tunneling, including shield attitude and total thrust. The model can achieve multi-ring predictions of shield attitude and total thrust by allocating larger weights to significant moments through a temporal attention mechanism. The hyperparameters of the proposed model are automatically selected through Bayesian hyperparameter optimization, which can effectively address the issue of complex parameter selection and optimization difficulties in multi-ring, multi-objective tasks. Based on the predictive results of the optimal model, an intelligent control method that considers both shield attitude and total thrust is proposed. Compared to a method that solely predicts and corrects for the next ring, the proposed multi-ring correction method provides the opportunity for further adjustments, if the initial correction falls short of expectations. A shield tunneling project in Hangzhou is used to demonstrate the effectiveness of the proposed model. The results show that the BOTA-LSTM model outperforms the models without the integration of a temporal attention mechanism and Bayesian hyperparameter optimization. The proposed multi-ring intelligent correction method can adjust the shield attitude and total thrust to a reasonable range, providing references for practical engineering applications.


  • Open Access

    A spatiotemporal deep learning method for excavation-induced wall deflections

    by Yuanqin Tao, Shaoxiang Zeng, Honglei Sun, Yuanqiang Cai, Jinzhang Zhang, Xiaodong Pan